EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Transferable deep generative modeling of intrinsically disordered protein conformations

Giacomo Janson, Michael Feig iD

PLOS Computational Biology · 2024

DOI: 10.1371/journal.pcbi.1012144 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2024. Verfasst von Giacomo Janson und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biochemistry and Molecular Biology, Michigan State University, East Lansing, Michigan, United States of America. Hauptthemen laut MEDLINE: Intrinsically Disordered Proteins, Protein Conformation, Neural Networks, Computer, Computational Biology. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 86 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, National Institute of General Medical Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intrinsically disordered proteins have dynamic structures through which they play key biological roles. The elucidation of their conformational ensembles is a challenging problem requiring an integrated use of computational and experimental methods. Molecular simulations are a valuable computational strategy for constructing structural ensembles of disordered proteins but are highly resource-intensive. Recently, machine learning approaches based on deep generative models that learn from simulation data have emerged as an efficient alternative for generating structural ensembles. However, such methods currently suffer from limited transferability when modeling sequences and conformations absent in the training data. Here, we develop a novel generative model that achieves high levels of transferability for intrinsically disordered protein ensembles. The approach, named idpSAM, is a latent diffusion model based on transformer neural networks. It combines an autoencoder to learn a representation of protein geometry and a diffusion model to sample novel conformations in the encoded space. IdpSAM was trained on a large dataset of simulations of disordered protein regions performed with the ABSINTH implicit solvent model. Thanks to the expressiveness of its neural networks and its training stability, idpSAM faithfully captures 3D structural ensembles of test sequences with no similarity in the training set. Our study also demonstrates the potential for generating full conformational ensembles from datasets with limited sampling and underscores the importance of training set size for generalization. We believe that idpSAM represents a significant progress in transferable protein ensemble modeling through machine learning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Intrinsically Disordered ProteinsProtein ConformationNeural Networks, ComputerComputational BiologyModels, MolecularMachine LearningDeep LearningAlgorithmsDatabases, Protein

Substanzen

Intrinsically Disordered Proteins

Autor:innen und Institutionen

  • Department of Biochemistry and Molecular Biology, Michigan State University, East Lansing, Michigan, United States of America.

ORCID-Profile: Michael Feig

Förderung

  • NIGMS NIH HHS
  • National Institute of General Medical Sciences

Zitieren

APA

Janson, G., & Feig, M. (2024). Transferable deep generative modeling of intrinsically disordered protein conformations. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1012144

Vancouver

Janson G, Feig M. Transferable deep generative modeling of intrinsically disordered protein conformations. PLOS Computational Biology. 2024. doi:10.1371/journal.pcbi.1012144

BibTeX
@article{Janson2024,
  author = {Janson, Giacomo and Feig, Michael},
  title = {Transferable deep generative modeling of intrinsically disordered protein conformations},
  journal = {PLOS Computational Biology},
  year = {2024},
  doi = {10.1371/journal.pcbi.1012144}
}
Kostenlos starten →